© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6787
    Prev
    Next
    INDEX
    Explanations

    various forms of code closure and block ending in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jant
    -0.47
     Schneider
    -0.47
    manuelle
    -0.47
    чё
    -0.46
     arrivant
    -0.46
    unque
    -0.44
     coleg
    -0.44
     rowspan
    -0.43
    IRUS
    -0.43
    νή
    -0.43
    POSITIVE LOGITS
     Италијани
    1.04
    rungsseite
    1.02
    oredCriteria
    0.96
    tagHelperRunner
    0.93
    endpush
    0.92
     виправивши
    0.89
    endregion
    0.86
    SharedDtor
    0.84
    UnsafeEnabled
    0.82
     "..\..\..\
    0.81
    Activations Density 0.129%

    No Known Activations